4 papers
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
Samuel Lewis-Lim, Xingwei Tan, Mario Sanger +2
Chain-of-thought (CoT) reasoning allows humans to inspect how large language models reach their answers, and oversee model behaviour. This reasoning comes at an increased inference…
Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models
Danae Sánchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras +1
Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoni…
Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao +1
Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and s…
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao +1
Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfait…